Litcius/Paper detail

Large Language Model-based Human-Agent Collaboration for Complex Task Solving

Xueyang Feng, Zhiyuan Chen, Yujia Qin, Yankai Lin, Chen Xu, Zhiyuan Liu, Ji-Rong Wen

202418 citationsDOIOpen Access PDF

Abstract

In recent developments within the research community, the integration of Large Language Models (LLMs) in creating fully autonomous agents has garnered significant interest.Despite this, LLM-based agents frequently demonstrate notable shortcomings in adjusting to dynamic environments and fully grasping human needs.In this work, we introduce the problem of LLM-based human-agent collaboration for complex task-solving, exploring their synergistic potential.To tackle the problem, we propose a Reinforcement Learning-based Human-Agent Collaboration method, ReHAC, which trains a policy model designed to determine the most opportune stages for human intervention within the task-solving process.We conduct experiments under real and simulated human-agent collaboration scenarios.Experimental results demonstrate that the synergistic efforts of humans and LLM-based agents significantly improve performance in complex tasks, primarily through well-planned, limited human intervention.Datasets and code are available at:

Topics & Concepts

Computer scienceTask (project management)Human–computer interactionKnowledge managementArtificial intelligenceNatural language processingSystems engineeringEngineeringMulti-Agent Systems and NegotiationRobotics and Automated SystemsSemantic Web and Ontologies